Hugging Face's logo

amd
/
Llama-2-7b-hf-awq-g128-int4-asym-fp16-onnx-hybrid

Text Generation
ONNX
English
llama
llama2
amd
meta
facebook
Model card Files Community
uday610 commited on
Commit
734d8e9
·
verified ·
1 Parent(s): 98a106e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -47,7 +47,9 @@ base_model:
47
  - PostProcessed to generate Hybrid Model
48
  -
49
  - ## Quick Start
50
- For quickstart, refer to AMD [RyzenAI-SW-EA](https://account.amd.com/en/member/ryzenai-sw-ea.html)
 
 
51
 
52
  #### Evaluation scores
53
  The perplexity measurement is run on the wikitext-2-raw-v1 (raw data) dataset provided by Hugging Face. Perplexity score measured for prompt length 2k is 5.6769.
 
47
  - PostProcessed to generate Hybrid Model
48
  -
49
  - ## Quick Start
50
+
51
+ For quickstart, refer to hybrid-llm-artifacts_1.3.zip available in [RyzenAI-SW-EA](https://account.amd.com/en/member/ryzenai-sw-ea.html)
52
+
53
 
54
  #### Evaluation scores
55
  The perplexity measurement is run on the wikitext-2-raw-v1 (raw data) dataset provided by Hugging Face. Perplexity score measured for prompt length 2k is 5.6769.